Three-dimensional point cloud edge point extraction method and device, electronic equipment and storage medium

Abstract

The invention discloses an edge point extraction method and device of a three-dimensional point cloud, electronic equipment and a storage medium, and belongs to the technical field of computers. The method comprises the steps of obtaining a first feature vector of a target optical storage device in a current time period; the first feature vector comprises a first element used for indicating an operation feature and a second element used for indicating a network communication feature; inputting the first feature vector into an execution time prediction model to obtain target time; the execution time prediction model is obtained by training by taking a first feature vector of each historical time period of the sample optical storage equipment as a training sample and taking sample time as a label corresponding to the training sample; the influence of the sample optical storage device executing the over-the-air upgrade operation at the sample time on the load side is smaller than a first threshold value; and controlling the target optical storage device to execute an over-the-air upgrade operation at the target time. According to the three-dimensional point cloud edge point extraction method disclosed by the invention, the precision of the extracted object edge points can be improved.

Description

Technical Field

[0001] The present application belongs to the field of computer technology, and in particular, relates to a method, device, electronic device and storage medium for extracting edge points of a three-dimensional point cloud. Background Art

[0002] In the field of 3D visual images, obtaining edge points of special-shaped objects (such as irregular objects and objects with arbitrary curved shapes) is widely used in 3D high-precision fields such as measurement, gluing guidance, and defect detection. Generally, edge data is obtained by obtaining neighborhood information around the point cloud data of the object, and then the edge points of the object are extracted from the edge data.

[0003] However, due to the interference or complex shape of the object's point cloud data, the accuracy of the extracted object edge points is usually low. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a method, device, electronic device and storage medium for extracting edge points of a three-dimensional point cloud to improve the accuracy of the extracted edge points of an object.

[0005] In a first aspect, the present application provides a method for extracting edge points of a three-dimensional point cloud, the method comprising:

[0006] Obtain three-dimensional point cloud data of the target object;

[0007] Get the curvature of each point in the target point cloud data;

[0008] Determine edge points in 3D point cloud data based on the curvature of each point.

[0009] According to the edge point extraction method of the three-dimensional point cloud of the present application, the three-dimensional point cloud data of the target object is obtained; the curvature of each point in the target point cloud data is obtained; based on the curvature of each point, the edge points in the three-dimensional point cloud data are determined in a manner to eliminate the interference of the complex shape of the target object on the edge point extraction, and the edge points of the target object are accurately determined based on the curvature of each point to improve the accuracy of the extracted edge points of the object.

[0010] According to one embodiment of the present application, obtaining the curvature of each point in the target point cloud data includes:

[0011] For each point, determine the target neighboring points of the point;

[0012] Get the curvature of a point based on the coordinates of the target's neighboring points.

[0013] According to an embodiment of the present application, obtaining the curvature of a point based on the coordinates of a target neighboring point includes:

[0014] Fit the coordinates of the target's neighboring points to obtain the target surface equation;

[0015] Based on the target surface equation, get the curvature of the point.

[0016] According to one embodiment of the present application, the curvature includes Gaussian curvature and / or mean curvature.

[0017] According to one embodiment of the present application, determining edge points in three-dimensional point cloud data based on the curvature of each point includes:

[0018] For each point, if the curvature of the point belongs to the target interval, the point is determined as an edge point.

[0019] According to one embodiment of the present application, obtaining three-dimensional point cloud data of a target object includes:

[0020] Obtain original three-dimensional point cloud data of the target object;

[0021] The original three-dimensional point cloud data is subjected to smoothing filtering processing to obtain three-dimensional point cloud data; the smoothing filtering processing includes at least one of removing outliers, median filtering, mean filtering and Gaussian filtering.

[0022] According to one embodiment of the present application, after determining edge points in the three-dimensional point cloud data based on the curvature of each point, the method further includes:

[0023] Perform smoothing filtering on the edge points to obtain the point cloud edge of the target object.

[0024] In a second aspect, the present application provides a device for extracting edge points of a three-dimensional point cloud, the device comprising:

[0025] A first acquisition module, used to acquire three-dimensional point cloud data of a target object;

[0026] The second acquisition module is used to obtain the curvature of each point in the target point cloud data;

[0027] The determination module is used to determine edge points in the three-dimensional point cloud data based on the curvature of each point.

[0028] According to the edge point extraction device of the three-dimensional point cloud of the present application, the three-dimensional point cloud data of the target object is obtained; the curvature of each point in the target point cloud data is obtained; based on the curvature of each point, the edge points in the three-dimensional point cloud data are determined in a manner to eliminate the interference of the complex shape of the target object on the edge point extraction, and the edge points of the target object are accurately determined based on the curvature of each point to improve the accuracy of the extracted edge points of the object.

[0029] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for extracting edge points of a three-dimensional point cloud as described in the first aspect above is implemented.

[0030] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for extracting edge points of a three-dimensional point cloud as described in the first aspect above.

[0031] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0033] Figure 1 This is one of the flow charts of the edge point extraction method of the three-dimensional point cloud provided in the embodiment of the present application;

[0034] Figure 2 This is the second flow chart of the edge point extraction method of the three-dimensional point cloud provided in the embodiment of the present application;

[0035] Figure 3 It is a structural schematic diagram of an edge point extraction device for a three-dimensional point cloud provided in an embodiment of the present application;

[0036] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0038] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0039] In combination with the accompanying drawings, the edge point extraction method of a three-dimensional point cloud, the edge point extraction device of a three-dimensional point cloud, the electronic device and the readable storage medium provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0040] Among them, the edge point extraction method of the three-dimensional point cloud can be applied to the terminal, and can be specifically executed by hardware or software in the terminal.

[0041] The terminal includes, but is not limited to, a portable communication device such as a mobile phone or tablet computer with a touch-sensitive surface (e.g., a touch screen display and / or a touch pad). It should also be understood that in some embodiments, the terminal may not be a portable communication device, but a desktop computer with a touch-sensitive surface (e.g., a touch screen display and / or a touch pad).

[0042] In the following various embodiments, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, a mouse and a joystick.

[0043] The edge point extraction method of a three-dimensional point cloud provided in an embodiment of the present application may be executed by an electronic device or a functional module or functional entity in the electronic device that can implement the edge point extraction method of a three-dimensional point cloud. The electronic devices mentioned in the embodiment of the present application include but are not limited to mobile phones, tablet computers, computers, cameras, and wearable devices. The edge point extraction method of a three-dimensional point cloud provided in an embodiment of the present application is described below using an electronic device as an example of the execution subject.

[0044] like Figure 1 As shown, the edge point extraction method of the three-dimensional point cloud includes: step 110, step 120 and step 130.

[0045] Step 110: Acquire three-dimensional point cloud data of the target object.

[0046] In actual implementation, the target object can be a three-dimensional solid figure such as a cylinder, a triangular pyramid, etc., and the target object can also be an irregular object of any shape, or an object of any curved surface shape. In short, the target object can be a three-dimensional object of any volume and any shape.

[0047] In actual implementation, the three-dimensional point cloud data of the target object can be a set of vectors obtained by mapping the target object into a three-dimensional coordinate system, where each point in the set contains three-dimensional coordinates, and the three-dimensional coordinates of each point can include color information (RGB) or reflection intensity information (Intensity).

[0048] In some embodiments, the original three-dimensional point cloud data of the target object can be obtained by a three-dimensional imaging sensor, and the original three-dimensional point cloud data can be preprocessed to obtain the three-dimensional point cloud data of the target object. The three-dimensional imaging sensor can be a binocular camera, a three-dimensional scanner, an RGB-D camera, or any theoretically feasible device, which is not specifically limited in this application.

[0049] Step 120: Obtain the curvature of each point in the target point cloud data.

[0050] In actual implementation, the target point cloud data may be a set of data in the three-dimensional point cloud data. For each point in the target point cloud data, the curvature of the point may be obtained based on the points near the point, and the curvature of each point in the target point cloud data may be obtained by analogy.

[0051] In actual implementation, the Gaussian curvature and / or the mean curvature of each point in the target point cloud data may be obtained.

[0052] Step 130: Determine edge points in the three-dimensional point cloud data based on the curvature of each point.

[0053] In actual execution, it is possible to determine whether each point is an edge point of the target object based on the curvature of the point, and extract the edge points in the three-dimensional point cloud data in sequence.

[0054] In some embodiments, after edge points in the three-dimensional point cloud data are extracted, the edge point data in the three-dimensional point cloud data may be processed to obtain a point cloud edge of the target object.

[0055] According to the edge point extraction method of the three-dimensional point cloud of the embodiment of the present application, the three-dimensional point cloud data of the target object is obtained; the curvature of each point in the target point cloud data is obtained; based on the curvature of each point, the edge points in the three-dimensional point cloud data are determined in a manner to eliminate the interference of the complex shape of the target object on the edge point extraction, and the edge points of the target object are accurately determined based on the curvature of each point to improve the accuracy of the extracted object edge points.

[0056] In some embodiments, for each point in the target point cloud data, a target neighboring point of the point may be determined; and based on the coordinates of the target neighboring point, the curvature of the point may be acquired.

[0057] In actual implementation, the number of target neighboring points may be changed, and the curvature of the point may be obtained based on the coordinates of the target neighboring points.

[0058] In actual execution, for each point in the target point cloud data, the target neighboring points of the point can be determined based on the target algorithm. The target algorithm can be a K-neighboring point algorithm, and for each point in the target point cloud data, the K points closest to the point in the target point cloud data are determined as the target neighboring points, where K is a positive integer greater than 1.

[0059] In actual implementation, the target algorithm can be an R neighboring point algorithm. For each point in the target point cloud data, the point is taken as the center of the sphere and R is the radius to determine the target sphere. All points in the target sphere are taken as the target neighboring points of the point, and R is a positive number.

[0060] In some embodiments, a target curve can be simulated based on each point in the target point cloud data and the target neighboring points of the point, and the curvature of the point can be obtained based on the target curve. Alternatively, a target equation can be fitted based on the target neighboring points, and the curvature of the point can be obtained based on the target equation.

[0061] According to the edge point extraction method of the three-dimensional point cloud in the embodiment of the present application, the target neighboring points of each point in the target point cloud data are determined; the curvature of the point is obtained based on the coordinates of the target neighboring points; and the edge points in the three-dimensional point cloud data are determined based on the curvature of each point, thereby eliminating the interference of the complex shape of the target object on the edge point extraction, and accurately determining the edge points of the target object based on the curvature of each point to improve the accuracy of the extracted edge points of the object.

[0062] In some embodiments, the coordinates of the target neighboring points are fitted to obtain the target surface equation; based on the target surface equation, the curvature of the point is obtained.

[0063] In actual implementation, the target surface equation may be a quadratic surface equation. The target surface equation may be obtained by fitting the target neighboring points using the least square method, or by using the moving least square method or other theoretically feasible algorithms. The target surface equation may be as follows:

[0064] z=f(x,y)=a+bx+cy+dx 2 +exy+ky 2 ;

[0065] Where x is the x-coordinate of the point, y is the y-coordinate of the point, z is the z-coordinate of the point, and a, b, c, d, e, and k are the coefficients to be determined.

[0066] According to the edge point extraction method of the three-dimensional point cloud in the embodiment of the present application, for each point in the target point cloud data, the target neighboring points of the point are determined; the coordinates of the target neighboring points are fitted to obtain the target surface equation; based on the target surface equation, the curvature of the point is obtained, and based on the curvature of each point, the edge points in the three-dimensional point cloud data are determined in a manner that eliminates the interference of the complex shape of the target object on the edge point extraction, and the edge points of the target object are accurately determined based on the curvature of each point to improve the accuracy of the extracted edge points of the object.

[0067] In some embodiments, the curvature may include Gaussian curvature and / or mean curvature.

[0068] In actual implementation, for each point in the target point cloud data, after fitting the target surface equation for the target neighboring points, the Gaussian curvature of the point can be obtained based on the target surface equation. In some embodiments, the Gaussian curvature of the point can be obtained according to the following formula:

[0069] After fitting the target neighboring points to the following target surface equation:

[0070] z=f(x,y)=a+bx+cy+dx 2 +exy+ky 2 ;

[0071] The Gaussian curvature of the point is obtained according to the following formula:

[0072]

[0073] f x =b+2dx+ey;

[0074] f y =c+ex+2ky;

[0075] f xx =2d;

[0076] f yy =2k;

[0077] f xy =e;

[0078] Among them, Kcurve represents the Gaussian curvature of the point.

[0079] In actual implementation, for each point in the target point cloud data, after fitting the target surface equation for the target neighboring points, the average curvature of the point can be obtained based on the target surface equation. In some embodiments, the average curvature of the point can be obtained according to the following formula:

[0080] After fitting the target neighboring points to the following target surface equation:

[0081] z=f(x,y)=a+bx+cy+dx 2 +exy+ky 2 ;

[0082] The average curvature of the point is obtained according to the following formula:

[0083]

[0084] f x =b+2dx+ey;

[0085] f y =c+ex+2ky;

[0086] f xx =2d;

[0087] f yy =2k;

[0088] f xy =e;

[0089] Among them, Hcurve represents the average curvature of the point.

[0090] In some embodiments, for each point in the target point cloud data, the Gaussian curvature of the point can be obtained as the curvature of the point, or the average curvature of the point can be obtained as the curvature; the curvature of the point can also be determined based on the Gaussian curvature and the average curvature of the point. In some embodiments, a first weight for the Gaussian curvature of the point and a second weight for the average curvature of the point can be obtained, and the curvature of the point can be obtained according to the following formula:

[0091] Q=r 1* Kcurve+r 2* Hcurve;

[0092] Among them, Q represents the curvature of the point, Kcurve represents the Gaussian curvature of the point, Hcurve represents the average curvature of the point, r1 represents the first weight, and r2 represents the second weight.

[0093] According to the edge point extraction method of the three-dimensional point cloud of the embodiment of the present application, for each point in the target point cloud data, the target neighboring points of the point are determined; the coordinates of the target neighboring points are fitted to obtain the target surface equation; based on the target surface equation, the curvature of the point is obtained, and based on the curvature of each point, the edge points in the three-dimensional point cloud data are determined, so that the acquired edge points can better express the edge information of the target object, and the process of acquiring the edge points is more efficient.

[0094] In some embodiments, for each point, if the curvature of the point belongs to the target interval, the point is determined to be an edge point.

[0095] In actual implementation, the target interval can be 0 to 1 or any interval. For example, when the target interval is 0 to 0.7, if the curvature of point S is 0.5, point S can be determined as an edge point. On the contrary, when the curvature of the point does not belong to the target interval, it is determined that the point is not an edge point.

[0096] According to the edge point extraction method of the three-dimensional point cloud in the embodiment of the present application, the curvature of each point in the target point cloud data is obtained, and when the curvature of the point belongs to the target interval, the point is determined as an edge point, so that the screened edge points are more accurate.

[0097] In some embodiments, the original three-dimensional point cloud data of the target object can be obtained; the original three-dimensional point cloud data is smoothed and filtered to obtain three-dimensional point cloud data; the smoothing filter processing includes removing outliers, median filtering, mean filtering and Gaussian filtering.

[0098] In actual implementation, the original three-dimensional point cloud data can be subjected to multiple smoothing filtering processes.

[0099] In actual implementation, the original three-dimensional point cloud data of the target object can be obtained through a three-dimensional imaging sensor, and the original three-dimensional point cloud data can be smoothed and filtered to obtain the three-dimensional point cloud data of the target object. The three-dimensional imaging sensor can be a binocular camera, a three-dimensional scanner, an RGB-D camera, or any theoretically feasible device, and this application does not make specific limitations on this.

[0100] In some embodiments, after acquiring the original three-dimensional point cloud data of the target object, discrete points in the original three-dimensional point cloud data can be removed based on outlier removal, median filtering, etc., and noise can be smoothed based on Gaussian filtering and edge features can be maintained.

[0101] In some embodiments, Gaussian filtering may be performed on the original three-dimensional point cloud data according to the following formula:

[0102]

[0103] Where Z new Indicates the calculation of the filtered Z value of the query point, Z i Represents the Z value of the neighborhood point, dis[i] represents the distance from each neighborhood point to the point, N represents the number of domain points, and disSigma represents the distance weight.

[0104] According to the edge point extraction method of the three-dimensional point cloud of the embodiment of the present application, the original three-dimensional point cloud data of the target object is obtained; the original three-dimensional point cloud data is smoothed and filtered to obtain the three-dimensional point cloud data; the smoothing filter processing includes removing outliers, median filtering, mean filtering and Gaussian filtering. At least one of the methods smoothes and removes noise on the original three-dimensional point cloud data to enhance the robustness of edge extraction.

[0105] In some embodiments, after edge points in the three-dimensional point cloud data are determined based on the curvature of each point, smoothing filtering is performed on the edge points to obtain the point cloud edge of the target object.

[0106] In actual implementation, the smoothing filter process includes at least one of outlier removal, median filtering, mean filtering and Gaussian filtering.

[0107] According to the edge point extraction method of the three-dimensional point cloud of the embodiment of the present application, after determining the edge points in the three-dimensional point cloud data, the edge points are smoothed and filtered to obtain the point cloud edge of the target object, thereby smoothing and denoising the edge point data and enhancing the robustness of the edge extraction.

[0108] In order to better understand the edge point extraction method of the three-dimensional point cloud provided in the embodiment of the present application, further explanation is given below. It should be understood that the discussion below is only exemplary.

[0109] The present application provides a method for extracting edge points of a three-dimensional point cloud. The specific steps can be as follows: Figure 2 As shown:

[0110] Step 210, obtaining original three-dimensional point cloud data of the target object; performing smoothing filtering on the original three-dimensional point cloud data to obtain three-dimensional point cloud data; the smoothing filtering processing includes removing outliers, median filtering, mean filtering and Gaussian filtering.

[0111] In actual implementation, the target object can be a three-dimensional solid figure such as a cylinder, a triangular pyramid, etc., and the target object can also be an irregular object of any shape, or an object of any curved surface shape. In short, the target object can be a three-dimensional object of any volume and any shape.

[0112] In actual implementation, the three-dimensional point cloud data of the target object can be a set of vectors obtained by mapping the target object into a three-dimensional coordinate system, where each point in the set contains three-dimensional coordinates, and the three-dimensional coordinates of each point can include color information (RGB) or reflection intensity information (Intensity).

[0113] In actual implementation, the original three-dimensional point cloud data can be subjected to multiple smoothing filtering processes.

[0114] In actual implementation, the original three-dimensional point cloud data of the target object can be obtained through a three-dimensional imaging sensor, and the original three-dimensional point cloud data can be smoothed and filtered to obtain the three-dimensional point cloud data of the target object. The three-dimensional imaging sensor can be a binocular camera, a three-dimensional scanner, an RGB-D camera, or any theoretically feasible device, and this application does not make specific limitations on this.

[0115] In some embodiments, after acquiring the original three-dimensional point cloud data of the target object, discrete points in the original three-dimensional point cloud data can be removed based on outlier removal, median filtering, etc., and noise can be smoothed based on Gaussian filtering and edge features can be maintained.

[0116] In some embodiments, Gaussian processing may be performed on the original three-dimensional point cloud data according to the following formula:

[0117]

[0118] Where Z new Indicates the calculation of the filtered Z value of the query point, Z i Represents the Z value of the neighborhood point, dis[i] represents the distance from each neighborhood point to the point, N represents the number of domain points, and disSigma represents the distance weight.

[0119] According to the edge point extraction method of the three-dimensional point cloud of the embodiment of the present application, the original three-dimensional point cloud data of the target object is obtained; the original three-dimensional point cloud data is smoothed and filtered to obtain the three-dimensional point cloud data; the smoothing filter processing includes removing outliers, median filtering, mean filtering and Gaussian filtering. At least one of the methods smoothes and removes noise on the original three-dimensional point cloud data to enhance the robustness of edge extraction.

[0120] Step 220: For each point in the target point cloud data, determine the target neighboring point of the point.

[0121] In actual execution, for each point in the target point cloud data, the target neighboring points of the point can be determined based on the target algorithm. The target algorithm can be a K-neighboring point algorithm, and for each point in the target point cloud data, the K points closest to the point in the target point cloud data are determined as the target neighboring points, where K is a positive integer greater than 1.

[0122] In actual implementation, the target algorithm can be an R neighboring point algorithm. For each point in the target point cloud data, the point is taken as the center of the sphere and R is the radius to determine the target sphere. All points in the target sphere are taken as the target neighboring points of the point, and R is a positive number.

[0123] Step 230: Fit the coordinates of the target neighboring points to obtain the target surface equation; based on the target surface equation, obtain the curvature of the point.

[0124] In actual implementation, the target surface equation may be a quadratic surface equation. The target surface equation may be obtained by fitting the target neighboring points using the least square method, or by using the moving least square method or other theoretically feasible algorithms. The target surface equation may be as follows:

[0125] z=f(x,y)=a+bx+cy+dx 2 +exy+ky 2 ;

[0126] Where x is the x-coordinate of the point, y is the y-coordinate of the point, z is the z-coordinate of the point, and a, b, c, d, e, and k are the coefficients to be determined.

[0127] According to the edge point extraction method of the three-dimensional point cloud in the embodiment of the present application, for each point in the target point cloud data, the target neighboring points of the point are determined; the coordinates of the target neighboring points are fitted to obtain the target surface equation; based on the target surface equation, the curvature of the point is obtained, and based on the curvature of each point, the edge points in the three-dimensional point cloud data are determined in a manner that eliminates the interference of the complex shape of the target object on the edge point extraction, and the edge points of the target object are accurately determined based on the curvature of each point to improve the accuracy of the extracted edge points of the object.

[0128] In some embodiments, the curvature may include Gaussian curvature and / or mean curvature.

[0129] In actual implementation, for each point in the target point cloud data, after fitting the target surface equation for the target neighboring points, the Gaussian curvature of the point can be obtained based on the target surface equation. In some embodiments, the Gaussian curvature of the point can be obtained according to the following formula:

[0130] After fitting the target neighboring points to the following target surface equation:

[0131] z=f(x,y)=a+bx+cy+dx 2 +exy+ky 2 ;

[0132] The Gaussian curvature of the point is obtained according to the following formula:

[0133]

[0134] f x =b+2dx+ey;

[0135] f y =c+ex+2ky;

[0136] f xx =2d;

[0137] fyy =2k;

[0138] f xy =e;

[0139] Among them, Kcurve represents the Gaussian curvature of the point.

[0140] In actual implementation, for each point in the target point cloud data, after fitting the target surface equation for the target neighboring points, the average curvature of the point can be obtained based on the target surface equation. In some embodiments, the average curvature of the point can be obtained according to the following formula:

[0141] After fitting the target neighboring points to the following target surface equation:

[0142] z=f(x,y)=a+bx+cy+dx 2 +exy+ky 2 ;

[0143] The average curvature of the point is obtained according to the following formula:

[0144]

[0145] f x =b+2dx+ey;

[0146] f y =c+ex+2ky;

[0147] f xx =2d;

[0148] f yy =2k;

[0149] f xy =e;

[0150] Among them, Hcurve represents the average curvature of the point.

[0151] In some embodiments, for each point in the target point cloud data, the Gaussian curvature of the point can be obtained as the curvature of the point, or the average curvature of the point can be obtained as the curvature; the curvature of the point can also be determined based on the Gaussian curvature and the average curvature of the point. In some embodiments, a first weight for the Gaussian curvature of the point and a second weight for the average curvature of the point can be obtained, and the curvature of the point can be obtained according to the following formula:

[0152] Q = r1*Kcurve+r2*Hcurve;

[0153] Among them, Q represents the curvature of the point, Kcurve represents the Gaussian curvature of the point, Hcurve represents the average curvature of the point, r1 represents the first weight, and r2 represents the second weight.

[0154] Step 240: When the curvature of the point belongs to the target interval, the point is determined as an edge point.

[0155] In actual implementation, the target interval can be 0 to 1 or any interval. For example, when the target interval is 0 to 0.7, if the curvature of point S is 0.5, point S can be determined as an edge point. On the contrary, when the curvature of the point does not belong to the target interval, it is determined that the point is not an edge point.

[0156] In some embodiments, after edge points in the three-dimensional point cloud data are determined based on the curvature of each point, smoothing filtering is performed on the edge points to obtain the point cloud edge of the target object.

[0157] In actual implementation, the smoothing filter process includes at least one of outlier removal, median filtering, mean filtering and Gaussian filtering.

[0158] The embodiment of the present application also provides a device for extracting edge points of a three-dimensional point cloud.

[0159] like Figure 3 As shown, the edge point extraction device 300 of the three-dimensional point cloud includes: a first acquisition module 310 , a second acquisition module 320 and a determination module 330 .

[0160] A first acquisition module 310 is used to acquire three-dimensional point cloud data of a target object;

[0161] The second acquisition module 320 is used to acquire the curvature of each point in the target point cloud data;

[0162] The determination module 330 is used to determine edge points in the three-dimensional point cloud data based on the curvature of each point.

[0163] According to the edge point extraction device of the three-dimensional point cloud of the embodiment of the present application, the three-dimensional point cloud data of the target object is obtained; the curvature of each point in the target point cloud data is obtained; based on the curvature of each point, the edge points in the three-dimensional point cloud data are determined in a manner to eliminate the interference of the complex shape of the target object on the edge point extraction, and the edge points of the target object are accurately determined based on the curvature of each point to improve the accuracy of the extracted edge points of the object.

[0164] In some embodiments, the second acquisition module 320 may include:

[0165] A first determining unit is used to determine, for each point, a target neighboring point of the point;

[0166] The first acquisition unit is used to acquire the curvature of a point based on the coordinates of a point adjacent to the target.

[0167] In some embodiments, the first acquisition unit is specifically used to:

[0168] Fit the coordinates of the target's neighboring points to obtain the target surface equation;

[0169] Based on the target surface equation, get the curvature of the point.

[0170] In some embodiments, the curvature comprises Gaussian curvature and / or mean curvature.

[0171] In some embodiments, the determination module 330 may include:

[0172] The second determining unit is configured to determine, for each point, the point as an edge point when the curvature of the point belongs to the target interval.

[0173] In some embodiments, the first acquisition module 310 may include:

[0174] A second acquisition unit, used to acquire original three-dimensional point cloud data of the target object;

[0175] The third acquisition unit is used to perform smoothing filtering processing on the original three-dimensional point cloud data to obtain three-dimensional point cloud data; the smoothing filtering processing includes at least one of removing outliers, median filtering, mean filtering and Gaussian filtering.

[0176] In some embodiments, the edge point extraction device 300 of the three-dimensional point cloud may further include:

[0177] The third acquisition module is used to perform smoothing filtering on the edge points to obtain the point cloud edge of the target object.

[0178] The edge point extraction device of the three-dimensional point cloud in the embodiment of the present application can be an electronic device, or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or it can be other devices other than the terminal. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc. It can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0179] The edge point extraction device of the three-dimensional point cloud in the embodiment of the present application can be a device with an operating system. The operating system can be a Microsoft (Windows) operating system, an Android (Android) operating system, an IOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0180] The edge point extraction device 300 of the three-dimensional point cloud provided in the embodiment of the present application can achieve Figure 1 to Figure 2 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0181] In some embodiments, Figure 4 As shown, an embodiment of the present application also provides an electronic device 400, including a processor 401, a memory 402, and a computer program stored in the memory 402 and executable on the processor 401. When the program is executed by the processor 401, each process of the above-mentioned three-dimensional point cloud edge point extraction method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0182] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0183] An embodiment of the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, each process of the above-mentioned three-dimensional point cloud edge point extraction method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0184] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0185] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above-mentioned edge point extraction method of the three-dimensional point cloud when executed by a processor.

[0186] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0187] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned three-dimensional point cloud edge point extraction method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0188] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0189] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0190] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0191] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0192] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0193] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A method for extracting edge points of a three-dimensional point cloud, characterized in that: include: Obtain three-dimensional point cloud data of the target object; Get the curvature of each point in the target point cloud data; Based on the curvature of each point, edge points in the three-dimensional point cloud data are determined.

2. The edge point extraction method of three-dimensional point cloud according to claim 1, characterized in that: The obtaining of the curvature of each point in the target point cloud data comprises: For each of the points, determining a target neighboring point of the point; Based on the coordinates of the target neighboring point, the curvature of the point is obtained.

3. The edge point extraction method of three-dimensional point cloud according to claim 2, characterized in that: The step of obtaining the curvature of the point based on the coordinates of the target neighboring point includes: Fitting the coordinates of the target neighboring points to obtain the target surface equation; Based on the target surface equation, the curvature of the point is obtained.

4. The edge point extraction method of three-dimensional point cloud according to claim 3, characterized in that: The curvature includes Gaussian curvature and / or mean curvature.

5. The method for extracting edge points of a three-dimensional point cloud according to claim 1, characterized in that: The step of determining edge points in the three-dimensional point cloud data based on the curvature of each point includes: For each of the points, if the curvature of the point belongs to the target interval, the point is determined as an edge point.

6. The method for extracting edge points of a three-dimensional point cloud according to any one of claims 1 to 5, characterized in that: The step of obtaining three-dimensional point cloud data of a target object includes: Obtain original three-dimensional point cloud data of the target object; The original three-dimensional point cloud data is subjected to smoothing filtering processing to obtain three-dimensional point cloud data; the smoothing filtering processing includes at least one of removing outliers, median filtering, mean filtering and Gaussian filtering.

7. The method for extracting edge points of a three-dimensional point cloud according to claim 1, characterized in that: After determining edge points in the three-dimensional point cloud data based on the curvature of each point, the method further includes: Perform smoothing filtering on the edge points to obtain the point cloud edge of the target object.

8. A device for extracting edge points of a three-dimensional point cloud, characterized in that: include: A first acquisition module, used to acquire three-dimensional point cloud data of a target object; The second acquisition module is used to obtain the curvature of each point in the target point cloud data; A determination module is used to determine edge points in the three-dimensional point cloud data based on the curvature of each point.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the edge point extraction method of the three-dimensional point cloud as described in any one of claims 1-7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for extracting edge points of a three-dimensional point cloud as described in any one of claims 1 to 7 is implemented.

Images